- Size
- 2.8B parameterscounted from the safetensors header on the Hub
- Licence
- custom, read it, MIT LicenseOur reading, check the licence: A custom licence we have not read for this model: other makers use the same name for different texts. Read the model's own licence file before you use it.Licence text
- On the Hub since
- 13 Dec 2023the date the repo was created
- Context length
- 2k tokensfrom the model's config
- Kind
- Base model (no base model declared on the Hub)PhiForCausalLM
- On Hugging Face
- microsoft/phi-2175k downloads in the last 30 days, 3.5k likes
Scores
- default setting42.5%Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
Epoch's name: phi-2. Best closed model on this set: gpt-3.5-turbo-1106, 58.1% (OpenAI). All 15 results
Epoch's name: phi-2. Best closed model on this set: gpt-3.5-turbo-1106, 87.4% (OpenAI). All 134 results
Epoch's name: phi-2. Best closed model on this set: gemini-1.5-pro-001, 89.2% (Google DeepMind). All 88 results
Epoch's name: phi-2. Best closed model on this set: gpt-4-0314, 95.3% (OpenAI). All 113 results
- Shots: 558.4%Stanford CRFM Leaderboard
- Shots: 556.3%Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
Epoch's name: phi-2. Best closed model on this set: gpt-4o-2024-11-20, 88.1% (OpenAI). All 217 results
- Shots: 1073.6%Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
- Shots: 1073.6%Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
Epoch's name: phi-2. Best closed model on this set: gpt-3.5-turbo-1106, 86.0% (OpenAI). All 70 results
Epoch's name: phi-2. Best closed model on this set: claude-2.0, 87.5% (Anthropic). All 115 results
Epoch's name: phi-2. Best closed model on this set: claude-3-opus-20240229, 88.5% (Anthropic). All 137 results
Claimed by the maker Claimed
The model card has no claimed scores in a machine-readable form (the card's model-index), so none are shown. The maker may give scores in the card text: read the card.
Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.
Independent scores from Epoch AI (CC-BY 4.0), fetched 19 Nov 2026: Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from ‘https://epoch.ai/benchmarks’ [online resource]. Each row links its own source. What the badges mean.
Run it yourself
Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 2.5 GB, worked out from the model's config (microsoft/phi-2), at 16-bit precision. Choose a machine above to see a verdict for each format. Method
GGUF for llama.cpp, Ollama, LM Studio and others
TheBloke/phi-2-GGUF (converted by TheBloke), 19k downloads. Sizes are the real files on the Hub, all parts added up.
| Format | Size | Memory needed | Get it |
|---|---|---|---|
| Q2_K | 1.1 GBfile size | 4.1 GB1.1 + 2.5 + 0.50 | Commandsllama.cpp llama-server -hf TheBloke/phi-2-GGUF:Q2_KOllama ollama run hf.co/TheBloke/phi-2-GGUF:Q2_KDownload hf download TheBloke/phi-2-GGUF --include "phi-2.Q2_K.gguf" --local-dir phi-2-GGUF |
| Q3_K_S | 1.2 GBfile size | 4.2 GB1.2 + 2.5 + 0.50 | Commandsllama.cpp llama-server -hf TheBloke/phi-2-GGUF:Q3_K_SOllama ollama run hf.co/TheBloke/phi-2-GGUF:Q3_K_SDownload hf download TheBloke/phi-2-GGUF --include "phi-2.Q3_K_S.gguf" --local-dir phi-2-GGUF |
| Q3_K_M | 1.4 GBfile size | 4.4 GB1.4 + 2.5 + 0.50 | Commandsllama.cpp llama-server -hf TheBloke/phi-2-GGUF:Q3_K_MOllama ollama run hf.co/TheBloke/phi-2-GGUF:Q3_K_MDownload hf download TheBloke/phi-2-GGUF --include "phi-2.Q3_K_M.gguf" --local-dir phi-2-GGUF |
| Q4_0 | 1.5 GBfile size | 4.5 GB1.5 + 2.5 + 0.50 | Commandsllama.cpp llama-server -hf TheBloke/phi-2-GGUF:Q4_0Ollama ollama run hf.co/TheBloke/phi-2-GGUF:Q4_0Download hf download TheBloke/phi-2-GGUF --include "phi-2.Q4_0.gguf" --local-dir phi-2-GGUF |
| Q3_K_L | 1.5 GBfile size | 4.5 GB1.5 + 2.5 + 0.50 | Commandsllama.cpp llama-server -hf TheBloke/phi-2-GGUF:Q3_K_LOllama ollama run hf.co/TheBloke/phi-2-GGUF:Q3_K_LDownload hf download TheBloke/phi-2-GGUF --include "phi-2.Q3_K_L.gguf" --local-dir phi-2-GGUF |
| Q4_K_S | 1.5 GBfile size | 4.5 GB1.5 + 2.5 + 0.50 | Commandsllama.cpp llama-server -hf TheBloke/phi-2-GGUF:Q4_K_SOllama ollama run hf.co/TheBloke/phi-2-GGUF:Q4_K_SDownload hf download TheBloke/phi-2-GGUF --include "phi-2.Q4_K_S.gguf" --local-dir phi-2-GGUF |
| Q4_K_M | 1.7 GBfile size | 4.7 GB1.7 + 2.5 + 0.50 | Commandsllama.cpp llama-server -hf TheBloke/phi-2-GGUF:Q4_K_MOllama ollama run hf.co/TheBloke/phi-2-GGUF:Q4_K_MDownload hf download TheBloke/phi-2-GGUF --include "phi-2.Q4_K_M.gguf" --local-dir phi-2-GGUF |
| Q5_0 | 1.8 GBfile size | 4.8 GB1.8 + 2.5 + 0.50 | Commandsllama.cpp llama-server -hf TheBloke/phi-2-GGUF:Q5_0Ollama ollama run hf.co/TheBloke/phi-2-GGUF:Q5_0Download hf download TheBloke/phi-2-GGUF --include "phi-2.Q5_0.gguf" --local-dir phi-2-GGUF |
| Q5_K_S | 1.8 GBfile size | 4.8 GB1.8 + 2.5 + 0.50 | Commandsllama.cpp llama-server -hf TheBloke/phi-2-GGUF:Q5_K_SOllama ollama run hf.co/TheBloke/phi-2-GGUF:Q5_K_SDownload hf download TheBloke/phi-2-GGUF --include "phi-2.Q5_K_S.gguf" --local-dir phi-2-GGUF |
| Q5_K_M | 1.9 GBfile size | 4.9 GB1.9 + 2.5 + 0.50 | Commandsllama.cpp llama-server -hf TheBloke/phi-2-GGUF:Q5_K_MOllama ollama run hf.co/TheBloke/phi-2-GGUF:Q5_K_MDownload hf download TheBloke/phi-2-GGUF --include "phi-2.Q5_K_M.gguf" --local-dir phi-2-GGUF |
| Q6_K | 2.1 GBfile size | 5.1 GB2.1 + 2.5 + 0.50 | Commandsllama.cpp llama-server -hf TheBloke/phi-2-GGUF:Q6_KOllama ollama run hf.co/TheBloke/phi-2-GGUF:Q6_KDownload hf download TheBloke/phi-2-GGUF --include "phi-2.Q6_K.gguf" --local-dir phi-2-GGUF |
| Q8_0 | 2.8 GBfile size | 5.8 GB2.8 + 2.5 + 0.50 | Commandsllama.cpp llama-server -hf TheBloke/phi-2-GGUF:Q8_0Ollama ollama run hf.co/TheBloke/phi-2-GGUF:Q8_0Download hf download TheBloke/phi-2-GGUF --include "phi-2.Q8_0.gguf" --local-dir phi-2-GGUF |
MLX for Apple silicon
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| MLX 4bitjesusoctavioas/phi-2-mlx-4Bit | 1.5 GBfile size | 4.5 GB1.5 + 2.5 + 0.50 | Download page |
| MLX 4bitSerhiiBzenko/phi-2-mlx-4Bit | 1.5 GBfile size | 4.5 GB1.5 + 2.5 + 0.50 | Download page |
Original weights size from the safetensors header, for vLLM, SGLang, Transformers
| Format | Size | Memory needed | Repo |
|---|---|---|---|
| F16original weights | 5.2 GBfile size | 8.2 GB5.2 + 2.5 + 0.50 |
hf download microsoft/phi-2 --local-dir phi-2Other conversions (12; sizes not read)
- mlc-ai/phi-2-q4f16_1-MLC Other, 1.8k downloads
- mlc-ai/phi-2-q4f32_1-MLC Other, 273 downloads
- TheBloke/phi-2-GPTQ GPTQ, 153 downloads
- junnyb/llamoco-phi2 bitsandbytes, 47 downloads
- OpenVINO/phi-2-int8-ov Other, int8, 42 downloads
- OpenVINO/phi-2-int4-ov Other, int4, 36 downloads
- leliuga/phi-2-bnb-4bit bitsandbytes, 4bit, 14 downloads
- Crusadersk/phi-2-gptq-4bit GPTQ, 4bit, 13 downloads
- liodon-ai/phi-2-FP8 FP8, 11 downloads
- jayantgurushrivastava/phi2-oasst-grpo bitsandbytes, 9 downloads
- Irfanuruchi/phi-2-chat bitsandbytes, 5 downloads
- STiFLeR7/Phi2-GPTQ GPTQ, 4 downloads
The Hub tags 64 quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.
Run it by API
No provider on Hugging Face Inference Providers serves this model (as of 19 Nov 2026, 13:58 UTC). Other hosts may; we only list what the router reports.
Not built yet: one key for every open model, with BlockRun, and our own tested-quality score per provider. Until then, precision and measured speed are the best guide to a provider here.
Planned for this page Not built yet
- Try it in private chat
- A link to Solana AI's confidential chat for the models it serves. This model is not listed as served there.
- Fine-tune it
- Fine-tuning a few base models from this page and publishing the result here.
- Creators and earnings
- Pages for people who publish fine-tunes and adapters of this model, and what they earn.
- Fund and bounties
- Bounties for new open models, paid from a public fund. How the fund will work.
- Contribute compute
- How to give compute to open model work, with Akash.
Model data from the Hugging Face Hub 19 Nov 2026, 13:43 UTC. The repo. Found a mistake on this page? Tell us.